Enhancing Student Satisfaction through Emotion Detection and Recognition using Computer Vision with Predictive Analytics

This study proposes an innovative method to enhance student satisfaction1 by integrating emotion detection2 and recognition using computer vision3 with visualization techniques4. Traditional methods like surveys often fail to capture the full scope of students' experiences. Our approach leverages real-time monitoring of students' emotional states to gain deeper insights into engagement and motivation, thereby improving overall satisfaction. The objectives include developing a real-time emotion monitoring system, integrating facial API and computer vision for emotional recognition, using visualization techniques for data analysis, and assessing system effectiveness using the FURPS criteria. The study's significance spans various stakeholders: students benefit from improved academic outcomes, educators can tailor their teaching methods, parents can better support their children, and institutions can enhance their programs. The research employs a quantitative descriptive design with participants from the computer science and digital animation programs, instructors, guidance counselors, and IT experts. Data will be collected through interviews, observations, and secondary sources. The project will be conducted over two semesters, with preliminary testing in the 2023-2024 academic year and full implementation in the 2024-2025 academic year. Using the Agile Model for development, the system will feature a virtual YouCam web camera for emotion detection, visualization techniques for data analysis, and facial recognition for attendance monitoring. Despite challenges like privacy concerns and data accuracy, the integration of predictive analytics aims to provide actionable insights to enhance student satisfaction and educational outcomes.